G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors

TL;DR

G-CAME is a fast, CAM-based explanation method for object detectors that uses Gaussian kernels to generate saliency maps, improving interpretability without significant computational cost.

Contribution

This paper introduces G-CAME, a novel Gaussian kernel-based CAM method that provides quick and effective explanations for object detection models like YOLOX and Faster R-CNN.

Findings

G-CAME produces high-quality saliency maps for object detection.

It significantly reduces explanation time compared to region-based methods.

Validated on MS-COCO 2017 with YOLOX and Faster R-CNN.

Abstract

Nowadays, deep neural networks for object detection in images are very prevalent. However, due to the complexity of these networks, users find it hard to understand why these objects are detected by models. We proposed Gaussian Class Activation Mapping Explainer (G-CAME), which generates a saliency map as the explanation for object detection models. G-CAME can be considered a CAM-based method that uses the activation maps of selected layers combined with the Gaussian kernel to highlight the important regions in the image for the predicted box. Compared with other Region-based methods, G-CAME can transcend time constraints as it takes a very short time to explain an object. We also evaluated our method qualitatively and quantitatively with YOLOX on the MS-COCO 2017 dataset and guided to apply G-CAME into the two-stage Faster-RCNN model.